IEEE Robotics & Automation Magazine - September 2022 - 68

Background
Until now, object rigidity has been one of the common
assumptions in robotic grasping and manipulation. Strictly
speaking, all objects deform upon force interaction. Rigidity is
a valid assumption when object deformation can be neglected
in a task. Nevertheless, many objects that need to be manipulated
by robots present nonnegligible deformation: from
microsurgical operation to challenging industrial assemblies.
Robots need to be capable of manipulating deformable
objects to operate in human environments. This capability
would benefit many application fields; however, it also poses
fundamental research challenges. In this article, we consider a
generalized concept of manipulation where grasping is also
part of the task. We will refer to the problem as DOM.
The tasks involved in DOM cover a broad spectrum (see
Figure 1). They include dressing assistance in elderly care,
cable harnessing in industrial automation, harvesting and
processing fruit and vegetables in agriculture, and surgical
operations in medical services, to name a few.
the following technical challenges:
●
On the technical side, addressing deformation introduces
the complication of sensing deformation
● the high number of degrees of freedom (DoF) of soft bodies
●
the complexity of nonlinearity in modeling deformation.
We believe that overcoming these challenges is not only
beneficial to DOM, but that it can further push toward
developing autonomous robots that can operate in unstructured
environments.
In recent years, there have been a few surveys on robotic
manipulation of deformable objects. Some surveys focus on
specific areas of DOM. The survey from Jiménez [6] focuses
on model-based manipulation planning. More recently, Herguedas
et al. [7] review works using multirobot systems for
DOM, while the work of [8] considers multimodal sensing.
The authors of [9] present the state of the art on deformable
object modeling for manipulation. There are also two comprehensive
surveys in the area. The survey in [10] reviews
and classifies the state of the art according to the object's physical
properties. Lately, [11] reported most recent advances in
modeling, learning, perception, and control in DOM.
In contrast with the mentioned surveys, which either focus
(a)
(b)
on reporting the progress of the field or on a specific area, this
article aims at identifying scientific challenges introduced by
object deformations and at projecting crucial future research
directions. As DOM is an emerging field of research where
there is still much to be done, in this article, previous works
and open problems are given equal weight. In addition, we
dedicate one section to discussing practical challenges in various
applications of DOM. We believe the article is the first of
its kind in the field of DOM.
A robotic framework designed to handle deformable
(c)
(d)
Figure 1. Applications involving manipulation of deformable
objects. (a) Dressing assistance [1], (b) cable harnessing [2], (c)
fruit harvesting [3], and (d) suturing [4].
Sensing
Hardware
* Tactile
* Vision
* Force
Robotic
Hardware
objects usually consists of five key components: gripper and
robot design, sensing, modeling, planning, and control (Figure 2).
To position the current research and identify future trends, we
conducted a survey on the future perspective of DOM. We
shared the survey with people working in related fields at various
career stages. They were asked to rate the importance and
research maturity of each of the five
identified key components, from 1 to 4,
with 1 being not important/low maturity
and 4 being very important/high
maturity. We received 31 answers; they
are summarized in Figure 3.
We consider promising directions
Hardware
* Rigid/Soft
Robots
* Gripper
Design
Software
Sensing Algorithm
Sensing
Figure 2. A typical robotic framework for handling deformable objects. In this particular
example, the framework addresses a wire harness [5].
68 * IEEE ROBOTICS & AUTOMATION MAGAZINE * SEPTEMBER 2022
Deformation
Modeling
Planning
Control
of research as those that have the highest
significance and the lowest research
maturity. Based on the survey, sensing
is the most promising one among all
subareas. This is probably due to the
current booming trend in deep learning,
which has offered many new
methods for processing sensory data.
In addition, sensing is the prerequisite
for subsequent steps, such as modeling,
planning, and control.
IEEE Robotics & Automation Magazine - September 2022

Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - September 2022
